Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0255. Min Range: -5.0255
Max Act: 5.0255. Min Act: -0.1700
Data Index: 5336441 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.8068. Min Act: -0.1700
Data Index: 8511606 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.7755. Min Act: -0.1699
Data Index: 205579 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.7130. Min Act: -0.1700
Data Index: 5507534 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5685276 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.6505. Min Act: -0.1700
Data Index: 4279884 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5880. Min Act: -0.1700
Data Index: 4710442 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.6505. Min Act: -0.1700
Data Index: 36271 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5880. Min Act: -0.1700
Data Index: 4178485 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5880. Min Act: -0.1700
Data Index: 377502 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5880. Min Act: -0.1700
Data Index: 4677779 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5568. Min Act: -0.1700
Data Index: 2525404 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5568. Min Act: -0.1700
Data Index: 4635202 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5568. Min Act: -0.1700
Data Index: 5151541 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5568. Min Act: -0.1700
Data Index: 6360710 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5568. Min Act: -0.1700
Data Index: 200507 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5255. Min Act: -0.1700
Data Index: 1703578 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.4943. Min Act: -0.1700
Data Index: 431618 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5255. Min Act: -0.1700
Data Index: 4882521 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0255. Min Range: -5.0255
Max Act: 4.5255. Min Act: -0.1700
Data Index: 3758126 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19